How to do RAG with Q&A Model when there is more than one input is needed to RAG processor?

[ramda1234786]

Hi All,

I am using Q&A model for RAG
The Q&A Model takes two inputs as question and context

{
		"question": "where live??",
		"context": "My name is Clara and I live in Madrid."
}

While doing neural search how i will pass the parameter for question and context
Where should i add the context? Or utilizing two paramters is not possible in OpenSearch RAG?

{
    "query": {
        "neural": {
            "neural_field_vector": {
                "query_text": {{question}},
                "model_id": "90tQBI0BCjm4TK7_mz2B",
                "k": 1
            }
        }
    },
    "size": 1,
	"_source": [ "neural_field"],
    "ext": {
        "generative_qa_parameters": {
            "llm_model": "bedrock/q&a model",
            "llm_question": {{question}},
            "conversation_id": "eHFSxIwBu3N8jyGnExM0",
            "context_size": 5,
            "interaction_size": 2,
            "timeout": 15        }
    }
}

Any example for Q&A models as we have only parameter like llm_question?

While creating connector, i am giving the request body as

"request_body": "{ \"question\": \"${parameters.question}\" , \"context\": \"${parameters.context}\"}"